This study empirically benchmarks classical and quantum machine learning models for image recognition, finding that while quantum models offer superior accuracy and resource efficiency at high dimensi…

The paper introduces a Jacobian-based spectral audit to evaluate neural operators, demonstrating that standard prediction error metrics fail to capture crucial local dynamical structures and operator…

The paper introduces the Computation-Aware State-Space Model (CASSM), a novel framework that extends Bayesian methods to handle model selection and large state-spaces, achieving competitive performanc…

The paper introduces a comprehensive benchmark to test if physics foundation models learn generalizable dynamics, finding that their performance is highly conditional and not universally general.

AdaKoop introduces an efficient streaming algorithm that models complex nonlinear dynamics from nonstationary data streams by leveraging the Koopman operator theory, achieving state-of-the-art accurac…

The paper introduces an Equilibrium Propagation (EP)-based training method for Predictive Coding Networks (PCNs), successfully training a large-scale VGG10 model on ImageNet and achieving state-of-the…

This paper proposes and evaluates the KAN-LSTM model, demonstrating that Kolmogorov-Arnold Networks (KANs) significantly outperform traditional deep learning models for accurate and parameter-efficien…

The paper proposes PG-RSSNN, a physics-guided recurrent state-space neural network that improves multi-step prediction stability and accuracy compared to both pure black-box and pure physics models, e…

This paper analyzes the multi-regime behavior of Scientific Machine Learning (SciML) models, finding that optimization effectiveness is regime-specific and that failure modes require a unified, regime…

DASH introduces a dual-branch distillation framework to effectively compress class-conditional diffusion models by independently supervising both score branches, significantly preserving guidance fide…

This paper proposes Supervised Memory Training (SMT), a method for training nonlinear RNNs that sidesteps recurrent credit propagation entirely.

This paper proposes Supervised Memory Training (SMT), a method for training nonlinear RNNs that sidesteps recurrent credit propagation entirely.

The paper demonstrates that the location and nature of state encoding in sequence models are not fixed architectural traits but are highly dependent on the specific task, showing that the encoding pro…

The paper proposes a multi-dimensional evaluation framework to assess EEG foundation models under realistic low-resource conditions, finding that while these models excel in long-context tasks, their…

The paper proposes Under-Cali, an uncertainty-driven dual-expert calibration framework, to achieve stable and efficient online forecasting for irregularly sampled multivariate time series.

The paper proposes two novel multi-column RBFN architectures, MC-PSO and MC-APSO, that combine parallel RBFN structures with swarm optimization to significantly outperform existing methods in accuracy…

The scaling exponent in neural scaling laws is not fixed but systematically depends on the optimizer used, with preconditioned optimizers generally yielding steeper scaling.